Akash Vartak
Computer Vision Research Assistant at University of Maryland Baltimore County
Baltimore, Maryland, United States
Summary
👤
Senior🎓
Top SchoolAkash Vartak is a Computer Vision Research Assistant and PhD student at UMBC's Coral Lab with 11 years of engineering experience blending deep learning research and practical software development. He focuses on Graph Neural Networks for model classification and adversarial detection, and his past work spans CNN-based vision and NLP-grounded visual perception. As a core contributor to the widely used PyTorch-Geometric project, he has improved type safety, test coverage, and added subgraph visualization for GNN explanations—efforts that bridge research prototypes and production-ready tooling. Proficient in Python, PyTorch, PyTorch-Geometric and Java, he actively seeks ML/AI research and project internships and collaborations. Colleagues describe him as someone who pairs rigorous academic inquiry with hands-on code improvements that make research systems more maintainable and interpretable.
11 years of coding experience
2 years of employment as a software developer
Bachelor’s Degree, Bachelor’s Degree at Pune Institute of Computer TechnologyUMBCHigh School, High School at St. Mary's Juniour College, Pune, MH, India.High School, High School at The Bishop's School, Pune, MH, India.
Marathi, Hindi, English
Stackoverflow
167reputation
328reached
6answers
0questions
Github Skills (19)
pytorch10
python10
testing10
typehinting10
deep-learning10
type-checking10
graph-neural-network10
machine-learning9
pytorch-geometric9
code-coverage9
graph-convolutional-networks8
html6
pygame6
css-animations6
responsive-design6
Programming languages (7)
Github contributions (5)
pyg-team/pytorch_geometric
Oct 2022 - Dec 2022
Graph Neural Network Library for PyTorch
Role in this project:
ML Engineer
ML EngineerContributions:11 commits, 19 PRs, 4 comments in 2 months
Contributions summary:Akash primarily focused on adding type hints and improving code coverage across various PyTorch Geometric library modules. Their contributions included adding type hints to utility functions and neural network pooling layers, enhancing code readability and maintainability. Furthermore, the user's work involved increasing code coverage through the addition of new test cases, specifically targeting modules related to assortativity, transforms, and home directory functionalities within the repository. The user also worked on subgraph visualization, adding capabilities for visualizing GNN explanations.
pytorchgraph-convolutional-networksgeometric-deep-learningdeep-learningneural-graph
akash-vartak/try
Jan 2015 - Dec 2016
Contributions:7 commits, 5 pushes, 1 branch in 1 year 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.